{"id":"W4284709654","doi":"10.1145/3510003.3510159","title":"CLEAR","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 44th International Conference on Software Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Task (project management); Natural language processing; Artificial intelligence; Word (group theory); Information retrieval; Embedding; Semantics (computer science); Programming language; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001689896,0.001632415,0.0009828237,0.003080508,0.001488039,0.004371091,0.002060412,0.001672081,0.1277634],"category_scores_gemma":[0.007465617,0.0007992721,0.001278308,0.002697927,0.0005984146,0.008078856,0.002925541,0.001712512,0.1623539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007560282,"about_ca_system_score_gemma":0.001600557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00507619,"about_ca_topic_score_gemma":0.006711119,"domain_scores_codex":[0.9975248,0.0003125843,0.0001932526,0.000733267,0.001000596,0.000235609],"domain_scores_gemma":[0.995627,0.0005993117,0.0002815614,0.00170557,0.001594327,0.0001921524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003591476,0.0001250791,0.00321436,0.0009726884,0.00008075906,0.0003329411,0.0002243243,0.001786829,0.0076345,0.03745823,0.4081528,0.5396584],"study_design_scores_gemma":[0.00003799892,0.00007034931,0.002888571,0.0001895075,0.00005408091,0.0006724136,0.0001918831,0.01437638,0.008497684,0.02000208,0.9529409,0.00007807639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01445527,0.006219913,0.4401936,0.004653733,0.002683435,0.001053172,0.039009,0.1251454,0.3665865],"genre_scores_gemma":[0.1252169,0.005158084,0.2672379,0.003846587,0.001037963,0.0007515481,0.127653,0.02170447,0.4473936],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1277634,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02487960478481576,"score_gpt":0.2298718623686812,"score_spread":0.2049922575838654,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}